GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
sandeepsawant28
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
sandeepsawant28
Model Tree
openai/whisper-small
Input Modalities
Output Modalities
Supported Functionality
openai/whisper-smalllanguage="mr" (Marathi) as the closest supported script/phonetic match, or with language auto-detectionVidyaapatiGU-Internship/ILCI_Agriculture_Speech_Corpus) — ~1,750 paired audio/transcript samples, ~1.7 hours of audio, agricultural domain, split 80/10/10 (train/val/test)ai4bharat/indicvoices_r, Konkani split) — broader general-domain Konkani speech, used to extend the initial adapter's coverage beyond agriculturePeftModel.from_pretrained, saved via PeftModel.save_pretrained — adapter-only checkpoints, not full Trainer checkpoints)| Metric | Value |
|---|---|
| Eval loss | 0.4633 |
| WER (validation) | 59.93% |
| CER (validation) | 23.73% |
| Training runtime | ~67 min (Colab T4) |
| WER (live test, 89 samples) | 76.18% |
Note: WER/CER remain relatively high, consistent with the low-resource nature of Konkani ASR and the limited training data volume. This adapter should be treated as an early-stage research checkpoint rather than a production-ready transcription system.
python
from transformers import WhisperForConditionalGeneration, WhisperProcessorfrom peft import PeftModelimport torch, librosa base_model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-small")model = PeftModel.from_pretrained(base_model, "sandeepsawant28/whisper-small-konkani-v2")model = model.to("cuda" if torch.cuda.is_available() else "cpu")model.eval() processor = WhisperProcessor.from_pretrained("openai/whisper-small") audio, sr = librosa.load("your_audio.wav", sr=16000)input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features.to(model.device) with torch.no_grad(): predicted_ids = model.generate(input_features, language="mr", task="transcribe") print(processor.batch_decode(predicted_ids, skip_special_tokens=True)[0])mr or auto-detect)Developed as part of the Vidyaapati Goa University Student Internship (VidyaapatiGU-Internship).
from transformers import WhisperForConditionalGeneration, WhisperProcessorfrom peft import PeftModelimport torch, librosa base_model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-small")model = PeftModel.from_pretrained(base_model, "sandeepsawant28/whisper-small-konkani-v2")model = model.to("cuda" if torch.cuda.is_available() else "cpu")model.eval() processor = WhisperProcessor.from_pretrained("openai/whisper-small") audio, sr = librosa.load("your_audio.wav", sr=16000)input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features.to(model.device) with torch.no_grad(): predicted_ids = model.generate(input_features, language="mr", task="transcribe") print(processor.batch_decode(predicted_ids, skip_special_tokens=True)[0])